Claude Opus 4.6

Anthropic

Parameters

—

Architecture

—

Released

—

License

—

Claude

About

No detailed description available for this model.

Benchmark Scores

Benchmark Score Date
AgentWorldBench MCP
general_agent
98.68%
24.06.2026
AgentWorldBench Search
general_agent
46.35%
24.06.2026
AgentWorldBench Terminal
general_agent
90.49%
24.06.2026
AgentWorldBench SWE
general_agent
87.31%
24.06.2026
AgentWorldBench Android
general_agent
100.00%
24.06.2026
AgentWorldBench Web
general_agent
57.14%
24.06.2026
AgentWorldBench OS
general_agent
100.00%
24.06.2026
AgentWorldBench Overall
general_agent
92.77%
24.06.2026
HLE (with tools)
stem_reasoning
75.64%
23.08.2026
BrowseComp
general_agent
91.49%
23.08.2026
DeepSearch QA
general_agent
88.89%
23.08.2026
Toolathlon Verified
general_agent
38.72%
23.08.2026
MCPMark
general_agent
59.00%
23.08.2026
Claw-Eval Pass^3
coding_agent
100.00%
23.08.2026
Claw-Eval Avg
coding_agent
100.00%
23.08.2026
Apex-Agents
general_agent
75.69%
23.08.2026
OSWorld-Verified
general_agent
75.41%
23.08.2026
Terminal-Bench 2.0
coding_agent
91.53%
23.08.2026
SWE-bench Pro
coding_agent
66.75%
23.08.2026
SWE-bench Multilingual
coding_agent
86.15%
23.08.2026
SWE-bench Verified
coding_agent
92.20%
23.08.2026
SciCode (subtask)
stem_reasoning
66.02%
23.08.2026
OJBench
stem_reasoning
84.73%
23.08.2026
LiveCodeBench v6
stem_reasoning
93.59%
23.08.2026
Humanity's Last Exam
stem_reasoning
71.78%
23.08.2026
AIME 26
stem_reasoning
96.81%
23.08.2026
HMMT Feb 26
stem_reasoning
98.06%
23.08.2026
IMOAnswerBench
stem_reasoning
74.86%
23.08.2026
GPQA Diamond
stem_reasoning
94.33%
23.08.2026
MMMU-Pro
vision_language
75.77%
23.08.2026
CharXiv (RQ)
document_understanding
12.25%
23.08.2026
MathVision
vision_language
48.65%
23.08.2026
BabyVision
vision_language
2.86%
23.08.2026
V-Star
vision_language
69.85%
23.08.2026

Related Models